Estimating the Difficulty of Exercises on Search Algorithms Using a Neuro-Fuzzy Approach

The delivery of educational activities that are tailored and adapted to the student knowledge level is a fundamental aspect of educational systems. In order to provide exercises and learning activities of appropriate difficulty, their level of difficulty should be accurately determined. In this paper, we present a neuro-fuzzy approach that determines the difficulty level of exercises on search algorithms. More specifically, the methodology presented, analyzes the exercises and estimates the difficulty level for blind search and heuristic search algorithmic exercises. Given that search algorithms act on trees, parameters like the number of the exercise´s nodes, the children for each level, the max depth of the tree and the length of the solution are taken into account. The system has been tested on a number of exercises for blind and heuristic search algorithms and its performance has been compared against that of expert tutors. The experimental results indicate quite promising performance.